Agri-R1: Empowering Generalizable Agricultural Reasoning in Vision-Language Models with Reinforcement Learning

• URL: http://arxiv.org/abs/2601.04672v1
• Date: Thu, 08 Jan 2026 07:34:37 GMT
• Title: Agri-R1: Empowering Generalizable Agricultural Reasoning in Vision-Language Models with Reinforcement Learning
• Authors: Wentao Zhang, Lifei Wang, Lina Lu, MingKun Xu, Shangyang Li, Yanchao Yang, Tao Fang,
• Abstract summary: We propose textbfAgri-R1, a reasoning-enhanced large model for agriculture.<n>Our framework high-quality reasoning data generation via vision-language synthesis and LLM-based filtering.<n>We show a +23.2% relative gain in disease recognition accuracy, +33.3% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization.
• Score: 22.34625628938106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel proposed reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +23.2\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. Ablation studies confirm that the synergy between structured reasoning data and GRPO-driven exploration underpins these gains, with benefits scaling as question complexity increases.

Related papers

• ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL [64.77036363086519]
  We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks.<n>We provide the reward model with full reference solutions as context, enabling fine-grained process verification to filter out false positives.<n>We also introduce a multi-turn sampling strategy where the reward model generates mistake reports for failed attempts, guiding the policy to "recover" correct responses from previously all-negative groups.
  arXiv  Detail & Related papers  (2026-02-26T04:55:57Z)
• Repurposing Synthetic Data for Fine-grained Search Agent Supervision [81.95597592711688]
  LLM-based search agents are increasingly trained on entity-centric synthetic data.<n> prevailing training methods discard this rich entity information, relying instead on sparse, outcome-based rewards.<n>We introduce Entity-aware Group Relative Policy Optimization (E-GRPO), a novel framework that formulates a dense entity-aware reward function.
  arXiv  Detail & Related papers  (2025-10-28T17:50:40Z)
• Optimizing Agricultural Research: A RAG-Based Approach to Mycorrhizal Fungi Information [1.2349443032034277]
  Retrieval-Augmented Generation (RAG) represents a transformative approach within natural language processing (NLP)<n>We present the design and evaluation of a RAG-enabled system tailored for Mycophyto.<n>The framework underscores the potential of AI-driven knowledge discovery to accelerate agroecological innovation and enhance decision-making in sustainable farming systems.
  arXiv  Detail & Related papers  (2025-09-16T20:21:55Z)
• Non-Linear Model-Based Sequential Decision-Making in Agriculture [0.0]
  Sequential decision-making is central to sustainable agricultural management and precision agriculture.<n>We propose a family of emphnonlinear, model-based bandit algorithms that embed domain-specific response curves directly into the exploration-exploitation loop.<n>Our approach supports sustainable, inclusive, and transparent sequential decision-making across agriculture, environmental management, and allied applications.
  arXiv  Detail & Related papers  (2025-09-02T03:41:48Z)
• AgriGPT: a Large Language Model Ecosystem for Agriculture [16.497060004913806]
  AgriGPT is a domain-specialized Large Language Models ecosystem for agriculture usage.<n>At its core, we design a scalable data engine that compiles credible data sources into Agri-342K, a high-quality, standardized question-answer dataset.<n>We employ Tri-RAG, a three-channel Retrieval-Augmented Generation framework combining dense retrieval, sparse retrieval, and multi-hop knowledge graph reasoning.
  arXiv  Detail & Related papers  (2025-08-12T04:51:08Z)
• Self-Consistency in Vision-Language Models for Precision Agriculture: Multi-Response Consensus for Crop Disease Management [0.0]
  This work presents a domain-aware framework for agricultural image processing that combines prompt-based expert evaluation with self-consistency mechanisms.<n>We introduce two key innovations: (1) a prompt-based evaluation protocol that configures a language model as an expert plant pathologist for scalable assessment of image analysis outputs, and (2) a cosine-consistency self-voting mechanism that generates multiple candidate responses from agricultural images.<n>Our approach improves diagnostic accuracy from 82.2% to 87.8%, symptom analysis from 38.9% to 52.2%, and treatment recommendation from 27.8% to 43.3
  arXiv  Detail & Related papers  (2025-07-08T18:32:21Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Federated In-Context Learning: Iterative Refinement for Improved Answer Quality [62.72381208029899]
  In-context learning (ICL) enables language models to generate responses without modifying their parameters by leveraging examples provided in the input.<n>We propose Federated In-Context Learning (Fed-ICL), a general framework that enhances ICL through an iterative, collaborative process.<n>Fed-ICL progressively refines responses by leveraging multi-round interactions between clients and a central server, improving answer quality without the need to transmit model parameters.
  arXiv  Detail & Related papers  (2025-06-09T05:33:28Z)
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization [50.91849555841057]
  Group Relative Policy Optimization is a reinforcement learning method for large reasoning models (LRMs)<n>We introduce a new Discriminative Constrained Optimization framework for reinforcing LRMs, grounded in the principle of discriminative learning.<n>DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7% over GRPO and 6% over DAPO.
  arXiv  Detail & Related papers  (2025-05-18T11:08:32Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
  Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance. We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination. We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T01:08:18Z)
• Biomedical knowledge graph-optimized prompt generation for large language models [1.6658478064349376]
  Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation framework.
  arXiv  Detail & Related papers  (2023-11-29T03:07:00Z)
• Minimizing Factual Inconsistency and Hallucination in Large Language Models [0.16417409087671928]
  Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance. We propose a multi-stage framework that generates the rationale first, verifies and refines incorrect ones, and uses them as supporting references to generate the answer. Our framework improves traditional Retrieval Augmented Generation (RAG) by enabling OpenAI GPT-3.5-turbo to be 14-25% more faithful and 16-22% more accurate on two datasets.
  arXiv  Detail & Related papers  (2023-11-23T09:58:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.